{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T04:05:25Z","timestamp":1781755525149,"version":"3.54.5"},"reference-count":83,"publisher":"Association for Computing Machinery (ACM)","issue":"7","funder":[{"name":"Natural Sciences and Engineering Research Council of Canada (NSERC) and Consortium for Research and Innovation in Aerospace in Qu\u00e9bec","award":["CRDPJ 537462-18"],"award-info":[{"award-number":["CRDPJ 537462-18"]}]},{"name":"Japan Science and Technology Agency (JST) Mirai Program","award":["JPMJMI20B8"],"award-info":[{"award-number":["JPMJMI20B8"]}]},{"name":"Japan Science and Technology Agency (JST) ASPIRE","award":["JPMJAP2301"],"award-info":[{"award-number":["JPMJAP2301"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Softw. Eng. Methodol."],"published-print":{"date-parts":[[2026,7,31]]},"abstract":"<jats:p>\n                    Deep Neural Networks (DNNs) are being utilized in various aspects of our daily lives, including high-stakes decision-making applications that impact individuals. However, these systems reflect and amplify bias from the data used during training and testing, potentially resulting in biased behavior and inaccurate decisions, for instance, having different misclassification rates between white and black sub-populations. However, effectively and efficiently identifying and correcting biased behavior in DNNs is a challenge. This article introduces\n                    <jats:monospace>FairFLRep<\/jats:monospace>\n                    , an automated fairness-aware fault localization and repair technique that identifies and corrects potentially bias-inducing neurons in DNN classifiers.\n                    <jats:monospace>FairFLRep<\/jats:monospace>\n                    focuses on adjusting neuron weights associated with sensitive attributes, such as race or gender, that contribute to unfair decisions. By analyzing the input\u2013output relationships within the network,\n                    <jats:monospace>FairFLRep<\/jats:monospace>\n                    corrects neurons responsible for disparities in predictive quality parity. We evaluate\n                    <jats:monospace>FairFLRep<\/jats:monospace>\n                    on four image classification datasets using two DNN classifiers, and four tabular datasets with a DNN model. The results show that\n                    <jats:monospace>FairFLRep<\/jats:monospace>\n                    consistently outperforms existing methods in improving fairness while preserving accuracy. An ablation study confirms the importance of considering fairness during both fault localization and repair stages. Our findings also show that\n                    <jats:monospace>FairFLRep<\/jats:monospace>\n                    is more efficient than the baseline approaches in repairing the network.\n                  <\/jats:p>","DOI":"10.1145\/3766890","type":"journal-article","created":{"date-parts":[[2025,9,10]],"date-time":"2025-09-10T14:04:24Z","timestamp":1757513064000},"page":"1-66","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["FairFLRep: Fairness-Aware Fault Localization and Repair of Deep Neural Networks"],"prefix":"10.1145","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4115-3834","authenticated-orcid":false,"given":"Moses","family":"Openja","sequence":"first","affiliation":[{"name":"Polytechnique Montreal, Montreal, Quebec, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6253-4062","authenticated-orcid":false,"given":"Paolo","family":"Arcaini","sequence":"additional","affiliation":[{"name":"National Institute of Informatics, Tokyo, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5704-4173","authenticated-orcid":false,"given":"Foutse","family":"Khomh","sequence":"additional","affiliation":[{"name":"Polytechnique Montreal, Montreal, Quebec, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7725-2618","authenticated-orcid":false,"given":"Fuyuki","family":"Ishikawa","sequence":"additional","affiliation":[{"name":"National Institute of Informatics, Tokyo, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,6,17]]},"reference":[{"key":"e_1_3_1_2_2","unstructured":"Mart\u00edn Abadi Ashish Agarwal Paul Barham Eugene Brevdo Zhifeng Chen Craig Citro Gregory S. Corrado Andy Davis Jeffrey Dean Matthieu Devin et al. 2016. TensorFlow: Large-scale machine learning on heterogeneous distributed systems. arXiv:1603.04467. Retrieved from https:\/\/arxiv.org\/abs\/1603.04467"},{"key":"e_1_3_1_3_2","unstructured":"Agency for Healthcare Research and Quality. 2018. Medical Expenditure Panel Survey Public Use File Details. Retrieved from https:\/\/meps.ahrq.gov\/mepsweb\/data_stats\/download_data_files_detail.jsp?cboPufNumber=HC-192"},{"key":"e_1_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.1145\/1985793.1985795"},{"key":"e_1_3_1_5_2","doi-asserted-by":"publisher","DOI":"10.24432\/C5XW20"},{"key":"e_1_3_1_6_2","doi-asserted-by":"publisher","DOI":"10.1147\/JRD.2019.2942287"},{"key":"e_1_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.1177\/0049124118782533"},{"key":"e_1_3_1_8_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE48619.2023.00134"},{"key":"e_1_3_1_9_2","first-page":"77","volume-title":"Proceedings of the 1st Conference on Fairness, Accountability and Transparency (Proceedings of Machine Learning Research, Vol. 81)","author":"Buolamwini Joy","year":"2018","unstructured":"Joy Buolamwini and Timnit Gebru. 2018. Gender shades: Intersectional accuracy disparities in commercial gender classification. In Proceedings of the 1st Conference on Fairness, Accountability and Transparency (Proceedings of Machine Learning Research, Vol. 81). PMLR, 77\u201391. Retrieved from https:\/\/proceedings.mlr.press\/v81\/buolamwini18a.html"},{"issue":"2","key":"e_1_3_1_10_2","doi-asserted-by":"crossref","first-page":"167","DOI":"10.1001\/amajethics.2019.167","article-title":"Can AI help reduce disparities in general medical and mental health care","volume":"21","author":"Chen Irene Y.","year":"2019","unstructured":"Irene Y. Chen, Peter Szolovits, and Marzyeh Ghassemi. 2019. Can AI help reduce disparities in general medical and mental health care? AMA Journal of Ethics 21, 2 (2019), 167\u2013179.","journal-title":"AMA Journal of Ethics"},{"key":"e_1_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2022.102444"},{"key":"e_1_3_1_12_2","doi-asserted-by":"publisher","DOI":"10.1145\/3652155"},{"key":"e_1_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.1089\/big.2016.0047"},{"key":"e_1_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.1145\/3682112.3682117"},{"issue":"1","key":"e_1_3_1_15_2","first-page":"14730","article-title":"2023. The measure and mismeasure of fairness","volume":"24","author":"Corbett-Davies Sam","year":"2023","unstructured":"Sam Corbett-Davies, Johann D. Gaebler, Hamed Nilforoshan, Ravi Shroff, and Sharad Goel. 2023. The measure and mismeasure of fairness. The Journal of Machine Learning Research 24, 1 (2023), 14730\u201314846.","journal-title":"The Journal of Machine Learning Research"},{"key":"e_1_3_1_16_2","doi-asserted-by":"publisher","DOI":"10.1145\/3097983.3098095"},{"key":"e_1_3_1_17_2","doi-asserted-by":"publisher","DOI":"10.24432\/C5TG7T"},{"key":"e_1_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671458"},{"key":"e_1_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.1089\/big.2016.0048"},{"key":"e_1_3_1_20_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-11009-3_35"},{"key":"e_1_3_1_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/MIS.2020.3000681"},{"key":"e_1_3_1_22_2","unstructured":"Chris Dulhanty and Alexander Wong. 2019. Auditing imageNet: Towards a model-driven framework for annotating demographic attributes of large-scale image datasets. arXiv:1905.01347. Retrieved from https:\/\/arxiv.org\/abs\/1905.01347"},{"key":"e_1_3_1_23_2","doi-asserted-by":"publisher","DOI":"10.1145\/2090236.2090255"},{"key":"e_1_3_1_24_2","unstructured":"European Commission. 2025. The EU Artificial Intelligence Act. Retrieved from https:\/\/artificialintelligenceact.eu\/"},{"key":"e_1_3_1_25_2","unstructured":"European Parliament and Council of the European Union. 2016. Regulation (EU) 2016\/679 of the European Parliament and of the Council. Retrieved from https:\/\/data.europa.eu\/eli\/reg\/2016\/679\/oj"},{"key":"e_1_3_1_26_2","doi-asserted-by":"publisher","DOI":"10.1145\/2783258.2783311"},{"key":"e_1_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.5555\/2969442.2969547"},{"key":"e_1_3_1_28_2","doi-asserted-by":"publisher","DOI":"10.1145\/3510003.3510087"},{"key":"e_1_3_1_29_2","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0306493"},{"key":"e_1_3_1_30_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISSRE59848.2023.00051"},{"key":"e_1_3_1_31_2","doi-asserted-by":"publisher","DOI":"10.18653\/V1\/N18-2017"},{"key":"e_1_3_1_32_2","doi-asserted-by":"publisher","DOI":"10.5555\/3157382.3157469"},{"key":"e_1_3_1_33_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_47"},{"key":"e_1_3_1_34_2","volume-title":"Workshop on Faces in \u2018Real-Life\u2019 Images: detection, Alignment, and Recognition","author":"Huang Gary B.","year":"2008","unstructured":"Gary B. Huang, Marwan Mattar, Tamara Berg, and Eric Learned-Miller. 2008. Labeled faces in the wild: A database for studying face recognition in unconstrained environments. In Workshop on Faces in \u2018Real-Life\u2019 Images: detection, Alignment, and Recognition."},{"key":"e_1_3_1_35_2","doi-asserted-by":"publisher","DOI":"10.1287\/mnsc.2020.3850"},{"key":"e_1_3_1_36_2","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00159"},{"key":"e_1_3_1_37_2","unstructured":"keras team. 2015. Keras: Deep Learning for Humans. Retrieved from https:\/\/github.com\/keras-team\/keras"},{"key":"e_1_3_1_38_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICST57152.2023.00030"},{"key":"e_1_3_1_39_2","doi-asserted-by":"crossref","first-page":"579","DOI":"10.1007\/s10664-016-9437-5","article-title":"Robust statistical methods for empirical software engineering","volume":"22","author":"Kitchenham Barbara","year":"2017","unstructured":"Barbara Kitchenham, Lech Madeyski, David Budgen, Jacky Keung, Pearl Brereton, Stuart Charters, Shirley Gibbs, and Amnart Pohthong. 2017. Robust statistical methods for empirical software engineering. Empirical Software Engineering 22 (2017), 579\u2013630.","journal-title":"Empirical Software Engineering"},{"key":"e_1_3_1_40_2","doi-asserted-by":"publisher","DOI":"10.1257\/pandp.20181018"},{"key":"e_1_3_1_41_2","doi-asserted-by":"crossref","first-page":"64","DOI":"10.1007\/978-3-030-76640-5_5","volume-title":"Artificial Intelligence and Machine Learning","author":"Kloos Kevin","year":"2021","unstructured":"Kevin Kloos, Quinten Meertens, Sander Scholtus, and Julian Karch. 2021. Comparing correction methods to reduce misclassification bias. In Artificial Intelligence and Machine Learning. Mitra Baratchi, Lu Cao, Walter A. Kosters, Jefrey Lijffijt, Jan N. van Rijn, and Frank W. Takes (Eds.), Springer International Publishing, Cham, 64\u201390."},{"key":"e_1_3_1_42_2","unstructured":"James Kuczmarski. 2018. Reducing Gender Bias in Google Translate. Retrieved from https:\/\/blog.google\/products\/translate\/reducing-gender-bias-google-translate\/"},{"key":"e_1_3_1_43_2","doi-asserted-by":"publisher","DOI":"10.1145\/3617168"},{"key":"e_1_3_1_44_2","doi-asserted-by":"publisher","DOI":"10.1109\/MCI.2024.3363984"},{"key":"e_1_3_1_45_2","doi-asserted-by":"publisher","DOI":"10.1145\/3583131.3590477"},{"key":"e_1_3_1_46_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICST57152.2023.00017"},{"key":"e_1_3_1_47_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19778-9_24"},{"key":"e_1_3_1_48_2","doi-asserted-by":"crossref","first-page":"60","DOI":"10.1016\/j.media.2017.07.005","article-title":"A survey on deep learning in medical image analysis","volume":"42","author":"Litjens Geert","year":"2017","unstructured":"Geert Litjens, Thijs Kooi, Babak Ehteshami Bejnordi, Arnaud Arindra Adiyoso Setio, Francesco Ciompi, Mohsen Ghafoorian, Jeroen Awm Van Der Laak, Bram Van Ginneken, and Clara I. S\u00e1nchez. 2017. A survey on deep learning in medical image analysis. Medical Image Analysis 42 (2017), 60\u201388.","journal-title":"Medical Image Analysis"},{"key":"e_1_3_1_49_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.425"},{"key":"e_1_3_1_50_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jss.2025.112475"},{"key":"e_1_3_1_51_2","doi-asserted-by":"publisher","DOI":"10.1145\/3705307"},{"key":"e_1_3_1_52_2","article-title":"FairGrad: Fairness aware gradient descent","author":"Maheshwari Gaurav","year":"2023","unstructured":"Gaurav Maheshwari and Micha\u00ebl Perrot. 2023. FairGrad: Fairness aware gradient descent. Transactions on Machine Learning Research. 2023. Retrieved from https:\/\/openreview.net\/forum?id=0f8tU3QwWD","journal-title":"Transactions on Machine Learning Research"},{"key":"e_1_3_1_53_2","doi-asserted-by":"publisher","DOI":"10.1145\/3457607"},{"key":"e_1_3_1_54_2","doi-asserted-by":"crossref","first-page":"61","DOI":"10.1007\/s10462-009-9137-2","article-title":"Recent advances in differential evolution: A survey and experimental analysis","volume":"33","author":"Neri Ferrante","year":"2010","unstructured":"Ferrante Neri and Ville Tirronen. 2010. Recent advances in differential evolution: A survey and experimental analysis. Artificial Intelligence Review 33 (2010), 61\u2013106.","journal-title":"Artificial Intelligence Review"},{"key":"e_1_3_1_55_2","doi-asserted-by":"publisher","DOI":"10.1145\/3611643.3616257"},{"key":"e_1_3_1_56_2","doi-asserted-by":"crossref","unstructured":"Moses Openja Paolo Arcaini Foutse Khomh and Fuyuki Ishikawa. 2025. Code and Results of the Paper \u201cFairFLRep: Fairness aware fault localization and repair of Deep Neural Networks\u201d. Retrieved from https:\/\/github.com\/openjamoses\/FairFLRep","DOI":"10.1145\/3766890"},{"key":"e_1_3_1_57_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10664-023-10409-5"},{"key":"e_1_3_1_58_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jss.2024.112244"},{"key":"e_1_3_1_59_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.swevo.2016.05.003"},{"key":"e_1_3_1_60_2","doi-asserted-by":"publisher","DOI":"10.5555\/3295222.3295319"},{"key":"e_1_3_1_61_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11721-007-0002-0"},{"key":"e_1_3_1_62_2","doi-asserted-by":"crossref","first-page":"108864","DOI":"10.1016\/j.patcog.2022.108864","article-title":"DARTSRepair: Core-failure-set guided DARTS for network robustness to common corruptions","volume":"131","author":"Ren Xuhong","year":"2022","unstructured":"Xuhong Ren, Jianlang Chen, Felix Juefei-Xu, Wanli Xue, Qing Guo, Lei Ma, Jianjun Zhao, and Shengyong Chen. 2022. DARTSRepair: Core-failure-set guided DARTS for network robustness to common corruptions. Pattern Recognition 131 (2022), 108864.","journal-title":"Pattern Recognition"},{"issue":"1","key":"e_1_3_1_63_2","doi-asserted-by":"crossref","first-page":"19","DOI":"10.1186\/s13636-022-00251-w","article-title":"Deep neural networks for automatic speech processing: A survey from large corpora to limited data","volume":"2022","author":"Roger Vincent","year":"2022","unstructured":"Vincent Roger, J\u00e9r\u00f4me Farinas, and Julien Pinquier. 2022. Deep neural networks for automatic speech processing: A survey from large corpora to limited data. EURASIP Journal on Audio, Speech, and Music Processing 2022, 1 (2022), 19.","journal-title":"EURASIP Journal on Audio, Speech, and Music Processing"},{"key":"e_1_3_1_64_2","unstructured":"Philipp Schmidt and Felix Bie\u00dfmann. 2019. Quantifying interpretability and trust in machine learning systems. arXiv:1901.08558. Retrieved from https:\/\/arxiv.org\/abs\/1901.08558"},{"key":"e_1_3_1_65_2","doi-asserted-by":"publisher","DOI":"10.1109\/SANER64311.2025.00040"},{"key":"e_1_3_1_66_2","doi-asserted-by":"publisher","DOI":"10.3390\/make1010010"},{"key":"e_1_3_1_67_2","doi-asserted-by":"publisher","DOI":"10.1145\/3563210"},{"key":"e_1_3_1_68_2","doi-asserted-by":"publisher","DOI":"10.1023\/A:1008202821328"},{"key":"e_1_3_1_69_2","doi-asserted-by":"publisher","DOI":"10.1109\/SANER53432.2022.00128"},{"key":"e_1_3_1_70_2","unstructured":"U.S. Equal Employment Opportunity Commission. 2025. Uniform Guidelines on Employee Selection Procedures. Retrieved from https:\/\/www.eeoc.gov\/"},{"key":"e_1_3_1_71_2","unstructured":"Christina Wadsworth Francesca Vera and Chris Piech. 2018. Achieving fairness through adversarial learning: An application to recidivism prediction. arXiv:1807.00199. Retrieved from https:\/\/arxiv.org\/abs\/1807.00199"},{"key":"e_1_3_1_72_2","doi-asserted-by":"publisher","DOI":"10.5555\/2349018"},{"key":"e_1_3_1_73_2","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2016.2521368"},{"key":"e_1_3_1_74_2","doi-asserted-by":"publisher","DOI":"10.1145\/3597926.3598099"},{"key":"e_1_3_1_75_2","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680638"},{"key":"e_1_3_1_76_2","doi-asserted-by":"publisher","DOI":"10.1109\/TR.2021.3096332"},{"key":"e_1_3_1_77_2","first-page":"962","volume-title":"Proceedings of the 20th International Conference on Artificial Intelligence and Statistics (Proceedings of Machine Learning Research, Vol. 54)","author":"Zafar Muhammad Bilal","year":"2017","unstructured":"Muhammad Bilal Zafar, Isabel Valera, Manuel Gomez Rogriguez, and Krishna P. Gummadi. 2017. Fairness constraints: Mechanisms for fair classification. In Proceedings of the 20th International Conference on Artificial Intelligence and Statistics (Proceedings of Machine Learning Research, Vol. 54). PMLR, 962\u2013970. Retrieved from https:\/\/proceedings.mlr.press\/v54\/zafar17a.html"},{"key":"e_1_3_1_78_2","doi-asserted-by":"publisher","DOI":"10.1145\/3278721.3278779"},{"key":"e_1_3_1_79_2","doi-asserted-by":"publisher","DOI":"10.1109\/ASE.2019.00043"},{"key":"e_1_3_1_80_2","doi-asserted-by":"publisher","DOI":"10.1145\/3377811.3380331"},{"issue":"1","key":"e_1_3_1_81_2","first-page":"931256","article-title":"A comprehensive survey on particle swarm optimization algorithm and its applications","author":"Zhang Yudong","year":"2015","unstructured":"Yudong Zhang, Shuihua Wang, and Genlin Ji. 2015. A comprehensive survey on particle swarm optimization algorithm and its applications. Mathematical Problems in Engineering. 2015, 1 (2015), 931256.","journal-title":"Mathematical Problems in Engineering"},{"key":"e_1_3_1_82_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.463"},{"key":"e_1_3_1_83_2","doi-asserted-by":"publisher","DOI":"10.18653\/V1\/D17-1323"},{"key":"e_1_3_1_84_2","doi-asserted-by":"publisher","DOI":"10.1145\/3510003.3510123"}],"container-title":["ACM Transactions on Software Engineering and Methodology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3766890","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T14:50:59Z","timestamp":1781707859000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3766890"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,17]]},"references-count":83,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2026,7,31]]}},"alternative-id":["10.1145\/3766890"],"URL":"https:\/\/doi.org\/10.1145\/3766890","relation":{},"ISSN":["1049-331X","1557-7392"],"issn-type":[{"value":"1049-331X","type":"print"},{"value":"1557-7392","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,17]]},"assertion":[{"value":"2024-11-05","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-09-03","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-06-17","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}